| abstract-reasoning-on-arc-agi-2 | GPT-6 Astra | #1 | Accuracy: 95.0 |
| agents-on-terminal-bench-science-0-1 | GPT-6 Astra | #1 | Accuracy: 64.6 |
| computer-use-agents-on-screenspot-pro | GPT-6 Astra (no tools) | #1 | Accuracy: 92.7 |
| exploit-generation-on-exploitbench | GPT-6 Astra | #1 | Coverage: 1.0 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | GPT-6 Astra | #1 | Accuracy: 96.0 |
| deep-research-agents-on-browsecomp | GPT-6 Astra | #2 | Accuracy: 91.5 |
| abstract-reasoning-on-arc-agi | GPT-6 Astra | #3 | Accuracy: 98.5 |
| code-generation-on-terminal-bench-4-0 | GPT-6 Astra | #3 | Accuracy: 57.9 |
| medical-question-answering-on-healthbench-professional | GPT-6 Astra | #3 | Score: 63.4 |
| code-generation-on-deepswe | GPT-6 Astra | #5 | Pass@1: 0.741 |